2022-2023年论文系列之模型轻量化和推理加速 前言 通过Connected Papers搜索引用PaBEE/DeeBERT/FastBERT的最新工作,涵盖: 模型推理加速 边缘设备应用 生成模型 BERT模型 知识蒸馏 论文目录 SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference SKDBERT: Compressing BERT via Stochastic Knowledge Distillation COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model Compression